Dopamine Modulates Option Generation for Behavior

Abstract

Animals make innumerable decisions every day, each of which involves evaluating potential options for action. But how are options generated? Although much is now known about decision making when a fixed set of potential options is provided, surprisingly little progress has been made on self-generated options. Some researchers have proposed that such abilities might be modulated by dopamine. Here, we used a new measure of option generation that is quantitative, objective, and culture fair to investigate how humans generate different behavioral options. Participants were asked to draw as many different paths (options) as they could between two points within a fixed time. Healthy individuals (n = 96) exhibited a trade-off between uniqueness (how individually different their options were) and fluency (number of options), generating either many similar or few unique options. To assess influence of dopamine, we first examined patients with Parkinson's disease (n = 35) ON and OFF their dopaminergic medication and compared them to elderly healthy controls (n = 34). Then we conducted a double-blind, placebo-controlled crossover study of the D2 agonist cabergoline in healthy older people (n = 29). Across both studies, dopamine increased fluency but diminished overall uniqueness of options generated, due to the effect of fluency trading off with uniqueness. Crucially, however, when this trade-off was corrected for, dopamine was found to increase uniqueness for any given fluency. Three carefully designed control studies showed that performance on our option-generation task was not related to executing movements, planning actions, or selecting between generated options. These findings show that dopamine plays an important role in modulating option generation.

Keywords: Parkinson’s disease; apathy; cabergoline; creativity; decision making; dopamine; option generation.

Graphical abstract

Figure 1

Option-Generation Task (A) The option-generation task required participants to draw, in 4 min, as many different paths as possible from the start point (bottom circle) to the end goal (top circle). Paths appeared as participants drew them and remained displayed on the touchscreen during the task so that participants did not have to remember them. (B) To quantify uniqueness, each path was first parameterized by 200 equally spaced points along its length. The “difference” between any two paths is then taken as the sum of the distance between corresponding points. This distance metric also includes the first and second derivatives in order to better account for curvatures in trajectories. Uniqueness of a path is then defined as the “distance” between it and the most similar path generated (by any participant in the three studies of this paper). Distances between a participant’s paths were also projected into a 2-dimensional subspace using multidimensional scaling to visualize how individuals explored the space of possible paths by treating each generated path as a point. Points that are closer together indicate more similar paths and vice versa. (C) Illustrations of the trajectories of the 69 paths generated by one participant (left), his corresponding points in 2-dimensional similarity subspace after multidimensional scaling (middle), and the pairwise distance matrix (right). See also Figure S1.

Figure 2

Results from the Option-Generation Task in Healthy People Each participant is represented by one point. (A) A scatterplot of the mean uniqueness against the number of paths generated, or fluency, revealed a uniqueness-fluency trade-off. Participants tended to either generate a few unique paths or many similar paths. (B) The number of paths generated on this task correlated positively with the level of motivation as indexed by a self-report measure. Thus, the more apathetic an individual, the fewer paths they were likely to generate. (C) The mean uniqueness of an individual’s paths is plotted against their motivation score. Motivated individuals generated less unique paths whereas apathetic people produced more unique paths. (D) Exploration was quantified by treating each generated path as a point in the individual’s 2-dimensional uniqueness subspace (see Figure 1C). The total “area” of different paths explored was defined as the area of a polygon surrounding all the path points (i.e., the convex hull). There was a trending negative correlation between explored area and motivation. This suggests a greater diversity of paths explored in apathetic individuals despite the fact that they generated a smaller number of paths, although that must be interpreted with caution.

Figure 3

Option-Generation Task Performance in Parkinson’s Disease versus Controls (A–C) PD patients generated significantly more paths when ON compared to OFF dopamine (p < 0.001) (A). Yet, they were more unique (p < 0.001) (B) and explored a larger area in the 2-dimensional path subspace (p < 0.05) (C) when OFF their medication. Healthy age-matched controls were both fluent and creative, generating a similar number of paths to patients ON dopamine and displaying comparable uniqueness and area of exploration to patients OFF dopamine. (D) A scatterplot of each individual’s mean uniqueness of paths against their number of paths generated. The same PD patients ON and OFF dopamine are connected by green lines. There appears to be a uniqueness-fluency trade-off between generating more paths and the uniqueness of these paths. (E) A comparison of the group averages in uniqueness and fluency shows that PD reduces fluency of generation, although uniqueness is preserved. Administration of dopamine restores the number of paths generated but at the expense of reduced uniqueness. This suggests that dopamine may play an important role in modulating the balance between generating more options against producing more unique outputs. (F) Because fluency correlates with uniqueness, a linear mixed effects model was used to examine how each path’s duration (or inverse of fluency) influences uniqueness. Dopamine was found to increase the uniqueness of paths after correcting for the fact that they were faster (red line significantly higher than blue line; p = 0.005). Error bars refer to one SE. HC, healthy controls; PD, Parkinson’s disease. See also Figures S2, S3, S4, S5, and S7 and Table S3.

Figure 4

Option-Generation Task Performance in Healthy Elderly People (n = 29) on Cabergoline and Placebo (Study 3) (A–C) Healthy people generated significantly more path options when they have taken cabergoline (dopamine D₂ agonist) compared to placebo (p < 0.001) (A). Yet they were more unique (p < 0.05) (B) and explored a larger area in the 2-dimensional path subspace (p < 0.05) (C) when they were on placebo. (D) A scatterplot of each individual’s mean uniqueness of paths against their number of paths generated. The same individual when on cabergoline and placebo are connected by green lines. (E) A mixed model applied to account for the correlation between fluency and uniqueness found that dopamine increases the uniqueness of paths for a given fluency (p < 0.001), which is consistent with what we have found from Parkinson’s disease patients in study 2. This increase is stronger in apathetic individuals. Error bars refer to one SE. See also Figures S2, S3, S4, and S7.

Figure 5

Results from Motor Execution Control Task (A) Participants had to draw ten straight lines, each as quickly as they could, from a start point (bottom circle) to an end goal (top circle). This serves as a baseline index of their motor vigor. (B) In healthy people (n = 96), the significant association between fluency in the option-generation task and individual level of motivation (reported above in Figure 2B) remains even after regressing out the mean time taken to draw each line. (C) In PD (n = 35), the difference in the number of paths generated for the option-generation task between the ON and OFF states did not correlate with their difference in mean drawing speed on the motor execution control task. (D) In healthy elderly people (n = 29), the difference in option generation fluency when on cabergoline and placebo also did not relate that in motor execution ability. These suggest that the reduced fluency in option generation when PD patients are OFF dopamine and when healthy people are on placebo is not attributable to impairments in movement speed or executing actions. See also Figure S6.

Figure 6

Results from Externally Cued Action Control Task (A) Participants were asked to join the bottom circle to as many target circles as possible in 90 s. Only one target, which was always red in color, appeared at a time. It turned gray after being touched, and then a new red target appeared. Thus, this task does not require either option generation or selection but requires motor planning of a different action each time. (B) In healthy people (n = 30), there was a significant correlation between fluency in the option-generation task and individual level of motivation even after regressing out the number of targets hit in this control task. (C) In PD (n = 35), the change in fluency in the option-generation task between the ON and OFF states did not relate to the change in the number of targets hit on the externally cued action control task. (D) In healthy elderly people (n = 29), the difference in option generation fluency when on cabergoline and placebo also did not relate that in motor planning ability. This indicates that reductions in fluency of option generation when PD patients are OFF dopamine and when healthy people are on placebo is not explained simply by deficits in planning or initiating actions. See also Figures S6 and S7.

Figure 7

Results from Option Selection Control Task (A) Participants had to join the bottom circle to as many target circles as possible in 90 s. They saw an array of 24 possible targets on the screen and were free to select any target they wanted for each connection (only 8 targets are illustrated here for simplicity). Thus, this task required selection between options, but not the generation of possible options. (B) In healthy people (n = 30), fluency in the option-generation task correlated with individual level of motivation even after accounting for the ability to select options. (C) In PD (n = 35), the difference in number of paths generated on the option-generation task between the ON and OFF states does not associate with the difference in number of paths drawn on the option selection control task. (D) In healthy elderly people (n = 28), the difference in option generation fluency when on cabergoline and placebo also did not relate that in option selection ability. This suggests that reductions in fluency of option generation when PD patients are OFF dopamine and when healthy people are on placebo is not simply due to impairments in selecting among generated options. See also Figures S6 and S7.